© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108331
    Prev
    Next
    INDEX
    Explanations

    Adapter Cable

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on numeric specification tokens—plain numbers (digits) and associated measurement values/units—in technical descriptions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    correctly
    -0.77
     Bion
    -0.75
    ці
    -0.74
    踪
    -0.73
    mina
    -0.72
    Marvin
    -0.72
     biotin
    -0.69
     ⇒
    -0.69
     Horus
    -0.68
     connais
    -0.68
    POSITIVE LOGITS
     lavander
    0.91
     female
    0.90
     FEMALE
    0.86
     Female
    0.81
     komputer
    0.81
     distinguer
    0.80
     cemento
    0.78
    CHK
    0.77
    AZZ
    0.77
     Negeri
    0.76
    Activations Density 0.009%

    No Known Activations